mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-27 16:35:01 +07:00
8ba306a6a3
If we restrict ourselves to only using a cacheline for each timeline's HWSP (we could go smaller, but want to avoid needless polluting cachelines on different engines between different contexts), then we can suballocate a single 4k page into 64 different timeline HWSP. By treating each fresh allocation as a slab of 64 entries, we can keep it around for the next 64 allocation attempts until we need to refresh the slab cache. John Harrison noted the issue of fragmentation leading to the same worst case performance of one page per timeline as before, which can be mitigated by adopting a freelist. v2: Keep all partially allocated HWSP on a freelist This is still without migration, so it is possible for the system to end up with each timeline in its own page, but we ensure that no new allocation would needless allocate a fresh page! v3: Throw a selftest at the allocator to try and catch invalid cacheline reuse. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: John Harrison <John.C.Harrison@Intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190128181812.22804-4-chris@chris-wilson.co.uk
90 lines
2.4 KiB
C
90 lines
2.4 KiB
C
/*
|
|
* Copyright © 2016 Intel Corporation
|
|
*
|
|
* Permission is hereby granted, free of charge, to any person obtaining a
|
|
* copy of this software and associated documentation files (the "Software"),
|
|
* to deal in the Software without restriction, including without limitation
|
|
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
|
|
* and/or sell copies of the Software, and to permit persons to whom the
|
|
* Software is furnished to do so, subject to the following conditions:
|
|
*
|
|
* The above copyright notice and this permission notice (including the next
|
|
* paragraph) shall be included in all copies or substantial portions of the
|
|
* Software.
|
|
*
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
|
|
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
|
|
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
|
|
* IN THE SOFTWARE.
|
|
*
|
|
*/
|
|
|
|
#include <linux/bitops.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/random.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/types.h>
|
|
|
|
#include "i915_random.h"
|
|
|
|
u64 i915_prandom_u64_state(struct rnd_state *rnd)
|
|
{
|
|
u64 x;
|
|
|
|
x = prandom_u32_state(rnd);
|
|
x <<= 32;
|
|
x |= prandom_u32_state(rnd);
|
|
|
|
return x;
|
|
}
|
|
|
|
void i915_prandom_shuffle(void *arr, size_t elsz, size_t count,
|
|
struct rnd_state *state)
|
|
{
|
|
char stack[128];
|
|
|
|
if (WARN_ON(elsz > sizeof(stack) || count > U32_MAX))
|
|
return;
|
|
|
|
if (!elsz || !count)
|
|
return;
|
|
|
|
/* Fisher-Yates shuffle courtesy of Knuth */
|
|
while (--count) {
|
|
size_t swp;
|
|
|
|
swp = i915_prandom_u32_max_state(count + 1, state);
|
|
if (swp == count)
|
|
continue;
|
|
|
|
memcpy(stack, arr + count * elsz, elsz);
|
|
memcpy(arr + count * elsz, arr + swp * elsz, elsz);
|
|
memcpy(arr + swp * elsz, stack, elsz);
|
|
}
|
|
}
|
|
|
|
void i915_random_reorder(unsigned int *order, unsigned int count,
|
|
struct rnd_state *state)
|
|
{
|
|
i915_prandom_shuffle(order, sizeof(*order), count, state);
|
|
}
|
|
|
|
unsigned int *i915_random_order(unsigned int count, struct rnd_state *state)
|
|
{
|
|
unsigned int *order, i;
|
|
|
|
order = kmalloc_array(count, sizeof(*order),
|
|
GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
|
|
if (!order)
|
|
return order;
|
|
|
|
for (i = 0; i < count; i++)
|
|
order[i] = i;
|
|
|
|
i915_random_reorder(order, count, state);
|
|
return order;
|
|
}
|